Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to consciousness and mental states

    oai_token-act-pair · gpt-3.5-turbo

    references to consciousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lot
    -0.69
    hire
    -0.68
     barrels
    -0.66
     teased
    -0.65
    Bench
    -0.64
     PLUS
    -0.63
    le
    -0.63
    ï¸ı
    -0.63
    vable
    -0.63
     refurb
    -0.62
    POSITIVE LOGITS
     consciousness
    3.83
     Conscious
    2.41
     conscious
    1.99
    conscious
    1.85
     awareness
    1.70
     unconscious
    1.54
    awareness
    1.40
     psyche
    1.39
     cognition
    1.35
     conscience
    1.35
    Act Density 0.008%

    No Known Activations